scrapely-python 0.1.23__py3-none-any.whl → 0.1.25__py3-none-any.whl

scrapely/__init__.py

@@ -227,7 +227,7 @@ if TYPE_CHECKING:  # Static analysers and IDEs see the lazy names as plain impor
         set_api_storage,
     )
 
-__version__ = '0.1.23'
+__version__ = '0.1.25'
 __all__ = [
     # Core
     'Actor',

scrapely/actor.py

@@ -360,6 +360,7 @@ class Actor(metaclass=_ActorMeta):
 
     @classmethod
     async def init(cls, options: Optional[InitOptions] = None) -> None:
+        cls._main_loop = asyncio.get_running_loop()  # for debug_capture_sync from worker threads
         if cls._initialized:
             return
 
@@ -922,6 +923,59 @@ class Actor(metaclass=_ActorMeta):
             cls._default_kvs = await cls.open_key_value_store()
         await cls._default_kvs.set_value(key, value, content_type=content_type)
 
+    # Debug capture: raw source payloads for platform diagnostics. Only active when the platform
+    # sets SCRAPELY_DEBUG_CAPTURE=1 on its own diagnostic runs; a no-op in every other run.
+    _DEBUG_CAPTURE_MAX_BYTES = 256 * 1024
+    _DEBUG_CAPTURE_MAX_RECORDS = 500
+    _debug_capture_count = 0
+
+    @staticmethod
+    def debug_capture_record_key(key: str) -> str:
+        """The key-value store record name for a capture key (item URL or id)."""
+        import hashlib
+        return 'DEBUG_CAPTURE_' + hashlib.sha1(str(key).strip().encode('utf-8')).hexdigest()[:24]
+
+    _main_loop: Optional[asyncio.AbstractEventLoop] = None
+
+    @classmethod
+    def debug_capture_sync(cls, key: str, payload: Any) -> None:
+        """debug_capture for synchronous code (also from worker threads, e.g. asyncio.to_thread).
+        Does nothing unless the platform enabled capture for this run."""
+        if os.environ.get('SCRAPELY_DEBUG_CAPTURE') != '1' or not key:
+            return
+        loop = cls._main_loop
+        if loop is None or loop.is_closed():
+            return
+        try:
+            try:
+                running = asyncio.get_running_loop()
+            except RuntimeError:
+                running = None
+            if running is loop:
+                loop.create_task(cls.debug_capture(key, payload))
+            else:
+                asyncio.run_coroutine_threadsafe(cls.debug_capture(key, payload), loop).result(timeout=15)
+        except Exception as err:  # never break the run
+            logging.getLogger('scrapely').debug('debug_capture_sync failed: %s', err)
+
+    @classmethod
+    async def debug_capture(cls, key: str, payload: Any) -> None:
+        """Save the raw source payload (API JSON or HTML) an item was extracted from, keyed by
+        the item's URL or id. Does nothing unless the platform enabled capture for this run."""
+        if os.environ.get('SCRAPELY_DEBUG_CAPTURE') != '1' or not key:
+            return
+        if cls._debug_capture_count >= cls._DEBUG_CAPTURE_MAX_RECORDS:
+            return
+        try:
+            text = payload if isinstance(payload, str) else json.dumps(payload, default=str, ensure_ascii=False)
+            if isinstance(text, bytes):
+                text = text.decode('utf-8', 'replace')
+            text = text[: cls._DEBUG_CAPTURE_MAX_BYTES]
+            cls._debug_capture_count += 1
+            await cls.set_value(cls.debug_capture_record_key(key), {'key': str(key), 'payload': text})
+        except Exception as err:  # never break the run
+            logging.getLogger('scrapely').debug('debug_capture failed: %s', err)
+
     @classmethod
     def _resolve_open_args(
         cls,

scrapely/proxy_configuration.py

@@ -203,7 +203,7 @@ def _platform_missing_error() -> str:
         'proxy credentials (SCRAPELY_PROXY_*/APIFY_PROXY_*) were injected into this '
         'environment. Run the actor on Scrapely with proxy access enabled, or remove the '
         'platform proxy entries. To use the platform proxy locally or from outside '
-        'Scrapely, copy your proxy credentials from the Scrapely console (Proxy page) '
+        'Scrapely, copy your proxy credentials from the Scrapely dashboard (Proxy page) '
         'into the SCRAPELY_PROXY_HOSTNAME, SCRAPELY_PROXY_PORT, SCRAPELY_PROXY_USERNAME '
         'and SCRAPELY_PROXY_PASSWORD environment variables (or pass password=... '
         'explicitly). External platform proxy access requires an active plan or a '
@@ -431,7 +431,7 @@ class ProxyConfiguration:
                 logger.warning(
                     'The Scrapely platform proxy is only available in on-platform runs when your '
                     'account has proxy access. Locally, either add proxy_urls to your actor input, '
-                    'or copy your proxy credentials from the Scrapely console (Proxy page) into the '
+                    'or copy your proxy credentials from the Scrapely dashboard (Proxy page) into the '
                     'SCRAPELY_PROXY_HOSTNAME, SCRAPELY_PROXY_PORT, SCRAPELY_PROXY_USERNAME and '
                     'SCRAPELY_PROXY_PASSWORD environment variables. Using the platform proxy from '
                     'outside Scrapely requires an active plan or a prepaid (PAYG) balance of at '

{scrapely_python-0.1.23.dist-info → scrapely_python-0.1.25.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: scrapely-python
-Version: 0.1.23
+Version: 0.1.25
 Summary: Scrapely Python SDK - A toolkit for building Actors on the Scrapely platform
 Author-email: Scrapely <support@scrape.ly>
 License-Expression: MIT AND Apache-2.0

{scrapely_python-0.1.23.dist-info → scrapely_python-0.1.25.dist-info}/RECORD

@@ -1,6 +1,6 @@
-scrapely/__init__.py,sha256=urKlJYfwafwGuUNCaDEPM0wK5H_krI8jYNKys8dsh9U,9661
+scrapely/__init__.py,sha256=2-L8VbKFypsPs_hl-GqCOKYwQvVcifUL4iXm0fOqhP4,9661
 scrapely/_browser_locations.py,sha256=8QVVnkms2bDn3_LDYgYDR59MvFx8757l_JYnZ7xb3oI,145269
-scrapely/actor.py,sha256=fNxlB2KxattbBh6aMo1p_ALrDQ3GdbJa03w_6DgIkjs,85310
+scrapely/actor.py,sha256=1SBHZYBRLmU4k_erjKL7yRfP0EgR7ZKXefAK8wWKRz0,88004
 scrapely/browser_configuration.py,sha256=jAZapNSHLFW05B96df4wNBtcyiiU9DA3ml0yTL1FwfA,5770
 scrapely/cdp_retry.py,sha256=hdTJEAIKhApM7IOk1DrQEl8NoflSJSmqd4RbNJ2IsgI,8540
 scrapely/charging.py,sha256=ns-kuUJtl8hBI4-3iBisC62BggJG67yYOa1yVVItoUI,83800
@@ -10,7 +10,7 @@ scrapely/errors.py,sha256=DCAlVvE3jToZuPEG2HVDL7i8D8hLboomQ5JpSOcsXoQ,4107
 scrapely/log.py,sha256=iVKoQdMLQXEWz1STzbSXrNUxsS_FNwiIdqoEg7CzeqU,1440
 scrapely/patch_browser_pool.py,sha256=R-1QDKa-ZvfdQ9wgyA8JCtmQqD9v7dOsaCZnSUoyf7U,42214
 scrapely/pricing_types.py,sha256=J6wCddZd-U1MYeOtaaEdeHSsp1HBgiQLfvSInBOvhIo,5305
-scrapely/proxy_configuration.py,sha256=4passyiUBfBsuzaBDyf5003rY0ayLYwwSnev0FaxCs0,38125
+scrapely/proxy_configuration.py,sha256=mQhUjXnqM1PcUrnRmXxVWdLnlaRlb8Je4K2j54lC6YQ,38129
 scrapely/py.typed,sha256=XtWlywqUjc6x_M2gAXlDtYXbAsYkCjKZEjFyJvaHvm4,105
 scrapely/solver.py,sha256=ahuORJwZu9aJzCKWF14qTjQSnwT6dEbhMophQQ03JHw,35854
 scrapely/types.py,sha256=ceVuHvhYbPai2CL3vFmXLTMoGaMR27IefJFgWhzd7ws,8900
@@ -39,10 +39,10 @@ scrapely/storage/_file_system/_key_value_store_client.py,sha256=4Ipgbh4qEqAkwQJ9
 scrapely/storage/_file_system/_storage_client.py,sha256=aaGJ4P0QAtIgEMl6yHpuobeWFD5M4rMC5HwhOOvuGuo,1794
 scrapely/storage_clients/__init__.py,sha256=cs1YX7JV2_GKBXeiiJgkQFali08b5_y_jH6Yw7iROAA,656
 scrapely/storages/__init__.py,sha256=4PAELhJNZ3exJ7Uouicn-bCQ58NafKjhLBixQ8ATQc4,173
-scrapely_python-0.1.23.dist-info/licenses/LICENSE,sha256=pQGY0XwjIYh-a2HfawxHq1en53bXkFkDj2Q70jKWHr4,1088
-scrapely_python-0.1.23.dist-info/licenses/LICENSE-APACHE,sha256=N8m0FzMq8i4UbTgXZvKEZJSD-27OF8pWZYS_atz4kTU,11355
-scrapely_python-0.1.23.dist-info/licenses/NOTICE,sha256=DEsNrw6UdSIqdYYqMWVFgJnyt6jUivTD7iFU6YM_e1A,1122
-scrapely_python-0.1.23.dist-info/METADATA,sha256=AY2FmyNKFInqRuBqZ2HnLSUVjz-UZ4bKeRTV5OsgPTU,3487
-scrapely_python-0.1.23.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
-scrapely_python-0.1.23.dist-info/top_level.txt,sha256=T4B9UMrs4q99QSAFyD1zdXhl40KnLhBKqrDkPhOTsmY,9
-scrapely_python-0.1.23.dist-info/RECORD,,
+scrapely_python-0.1.25.dist-info/licenses/LICENSE,sha256=pQGY0XwjIYh-a2HfawxHq1en53bXkFkDj2Q70jKWHr4,1088
+scrapely_python-0.1.25.dist-info/licenses/LICENSE-APACHE,sha256=N8m0FzMq8i4UbTgXZvKEZJSD-27OF8pWZYS_atz4kTU,11355
+scrapely_python-0.1.25.dist-info/licenses/NOTICE,sha256=DEsNrw6UdSIqdYYqMWVFgJnyt6jUivTD7iFU6YM_e1A,1122
+scrapely_python-0.1.25.dist-info/METADATA,sha256=9aB0qUPYZPSoRBuYQUIWWFQRnLrxpG66yP_ES6q_ZG8,3487
+scrapely_python-0.1.25.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+scrapely_python-0.1.25.dist-info/top_level.txt,sha256=T4B9UMrs4q99QSAFyD1zdXhl40KnLhBKqrDkPhOTsmY,9
+scrapely_python-0.1.25.dist-info/RECORD,,